Package org.tweetyproject.machinelearning.rl.mdp

package org.tweetyproject.machinelearning.rl.mdp
  • Class
    Description
    Action
    An action in a Markov Decision Process
    Episode<S extends State,A extends Action>
    This class models an episode in MPDs, i.e.
    FixedPolicy<S extends State,A extends Action>
    A fixed policy for MDPs, i.e., a simple map from states to actions.
    MarkovDecisionProcess<S extends State,A extends Action>
    This class models a Markov Decision Process (MDP, for fixed starting and terminal states), which can be used to represent reinforcement learning scenarios.
    NamedAction
    An action in a Markov Decision Process that is solely characterized through its name.
    NamedState
    A state in a Markov Decision Process that is solely characterized through its name.
    Policy<S extends State,A extends Action>
    A policy (map from states to actions) for Markov Decision Process
    State
    A state in a Markov Decision Process